Human-Like and Male? How AI Assistant Design Relates to Trust and Monetary Reward at Work in VR

Abstract

AI assistants are increasingly framed as digital coworkers rather than tools. In immersive settings such as VR, AI embodiment design choices can become salient social signals that shape human–AI interaction. We investigate how such choices influence users’ perceptions of and behavior toward AI coworkers by employing three functionally identical AI assistants varying in human-likeness and gender presentation. In a controlled study, 189 knowledge workers completed work tasks with them, provided ratings, and allocated monetary rewards; we additionally interviewed 34 participants. Our results show differences in reward allocation: more human-like assistants were paid more, and the female-presenting assistant was perceived as less human-like and rewarded less than the male-presenting counterpart. Yet, in interviews, many participants stated a preference for non-human-like assistants and that gender was irrelevant. We discuss how participants’ stated preferences relate to their evaluations and reward allocation behavior, and the implications of these findings for AI embodiment choices in workplace contexts.